Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mizukaizen/hive-doctrine-mcp --skill blog-writinggit clone --depth 1 https://github.com/mizukaizen/hive-doctrine-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/blog-writing)<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/blog-writing"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/blog-writing/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mizukaizen/hive-doctrine-mcp/blog-writing"><img src="https://agentmods.dev/badge/skills/mizukaizen/hive-doctrine-mcp/blog-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00000 | $0.00772 |
| Opus 5.5 | $0.00000 | $0.00309 |
| Sonnet 5.5 | $0.00000 | $0.00154 |
| Haiku 4.5 | $0.00000 | $0.00077 |
Grade A, and why
blog-writing scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Skill: Blog Writing
Use when creating a blog post from scratch. Guides the full process from topic research through to a publish-ready draft with proper SEO structure and heading hierarchy.
Trigger
Invoke this skill when the user wants to write a blog post, create long-form content, or needs help with an article. Also activates when the /draft command is used.
Process
1. Topic Validation
Before writing, confirm:
- Target keyword exists: Is anyone searching for this?
- Competition is manageable: Can you realistically rank?
- You have something to add: What angle is missing from existing content?
If any answer is "no," suggest alternative topics before proceeding.
2. Search Intent Alignment
Determine what the searcher actually wants:
- Informational: They want to learn. Write a comprehensive guide.
- Comparison: They want to choose. Write a balanced comparison with a recommendation.
- How-to: They want to do. Write step-by-step instructions with examples.
- List: They want options. Write a curated list with context for each item.
Match your content structure to the intent. A how-to post structured as a listicle will frustrate readers.
3. Outline Creation
Build the skeleton before writing:
- H1 (title): Includes primary keyword, under 60 characters, promises clear value
- Introduction (no heading): 2-3 sentences. State the problem, hint at the solution, establish credibility.
- H2 sections (3-6): Each answers one question the reader has. Logical flow from one to the next.
- H3 subsections: Break down complex H2 sections. Not every H2 needs H3s.
- Conclusion H2: Summary of key points, clear next step, call to action.
4. Drafting Guidelines
- First paragraph: Must contain the primary keyword and establish what the reader will learn.
- Body paragraphs: 3-4 sentences max. One idea per paragraph.
- Examples: At least one concrete example per major section. Abstract advice without examples is forgettable.
- Transitions: Each section should flow logically into the next. If it does not, the outline needs restructuring.
- Formatting: Use bold for key phrases, bullet points for lists of 3+, code blocks for technical content.
- Length: 1,500-2,500 words for most topics. Go longer only if the depth demands it.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2mo ago First seen · 77 lines · 0 tokens per session scan A 71c7ae7b2eb6
blog-writing is a skill published in the GitHub repository mizukaizen/hive-doctrine-mcp (0 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 772 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
blog-writing compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| blog-writingmizukaizen/hive-doctrine-mcp | Skill | 0 | 4mo ago | MIT | A | 0 | Claude Code, Codex |
| jev-desktopopenwong2kim/wmux | Skill | 448 | yesterday | MIT | A | 125 | Claude Code, Codex |
| agent-desktop-ffiopenwong2kim/wmux | Skill | 448 | yesterday | MIT | A | 122 | Claude Code, Codex |
| agent-desktopopenwong2kim/wmux | Skill | 448 | yesterday | MIT | A | 161 | Claude Code, Codex |
| agent-desktop-macosopenwong2kim/wmux | Skill | 448 | yesterday | MIT | A | 115 | Claude Code, Codex |
| agent-desktop-windowsopenwong2kim/wmux | Skill | 448 | yesterday | MIT | A | 119 | Claude Code, Codex |
| coding-agents-farmgriddynamics/rosetta | Skill | 373 | yesterday | Apache-2.0 | B | 32 | Claude Code |